Finding experiments¶
To use incense we first have to instantiate an experiment loader that will enable us to query the database for specific runs.
| targets_type | iteration | autoencoder_type | batch_size | artifacts | |
|---|---|---|---|---|---|
| exp_id | |||||
| 50 | Mnist | False | nomal_dim_tied_iteration | 256 | {'history_autoencoder_iteration': Artifact(nam... |
| 51 | Mnist | False | nomal_dim_tied_iteration | 128 | {'history_autoencoder_iteration': Artifact(nam... |
| 52 | Mnist | False | nomal_dim_tied_iteration | 64 | {'history_autoencoder_iteration': Artifact(nam... |
| 53 | Mnist | False | nomal_dim_tied_iteration | 32 | {'history_autoencoder_iteration': Artifact(nam... |
| 54 | 10_Targets | False | nomal_dim_tied_iteration | 256 | {'history_autoencoder_iteration': Artifact(nam... |
| 55 | 10_Targets | False | nomal_dim_tied_iteration | 128 | {'history_autoencoder_iteration': Artifact(nam... |
| 56 | 10_Targets | False | nomal_dim_tied_iteration | 64 | {'history_autoencoder_iteration': Artifact(nam... |
| 57 | 10_Targets | False | nomal_dim_tied_iteration | 32 | {'history_autoencoder_iteration': Artifact(nam... |
| targets_type | iteration | autoencoder_type | batch_size | artifacts | sort | |
|---|---|---|---|---|---|---|
| exp_id | ||||||
| 54 | 10_Targets | False | nomal_dim_tied_iteration | 256 | {'history_autoencoder_iteration': Artifact(nam... | 0 |
| 55 | 10_Targets | False | nomal_dim_tied_iteration | 128 | {'history_autoencoder_iteration': Artifact(nam... | 1 |
| 56 | 10_Targets | False | nomal_dim_tied_iteration | 64 | {'history_autoencoder_iteration': Artifact(nam... | 2 |
| 57 | 10_Targets | False | nomal_dim_tied_iteration | 32 | {'history_autoencoder_iteration': Artifact(nam... | 3 |
| 50 | Mnist | False | nomal_dim_tied_iteration | 256 | {'history_autoencoder_iteration': Artifact(nam... | 4 |
| 51 | Mnist | False | nomal_dim_tied_iteration | 128 | {'history_autoencoder_iteration': Artifact(nam... | 5 |
| 52 | Mnist | False | nomal_dim_tied_iteration | 64 | {'history_autoencoder_iteration': Artifact(nam... | 6 |
| 53 | Mnist | False | nomal_dim_tied_iteration | 32 | {'history_autoencoder_iteration': Artifact(nam... | 7 |
Red best overall, and also best of subset. Bes means for accuracy max, rest min. Green best of subset.
predictions_df_0
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.8619 | 0.8368 | 0.7321 | 0.7162 | 0.9721 | 0.9693 | 0.9746 | 0.9722 |
| 1 | 0.695 | 0.675 | 0.483 | 0.5107 | 0.9675 | 0.961 | 0.9691 | 0.9673 |
| 2 | 0.6564 | 0.6269 | 0.4355 | 0.4745 | 0.9423 | 0.9471 | 0.9566 | 0.9583 |
| 3 | 0.6418 | 0.5991 | 0.4196 | 0.4656 | 0.8961 | 0.9286 | 0.9341 | 0.9401 |
| 4 | 0.6298 | 0.5899 | 0.4156 | 0.4629 | 0.8441 | 0.9046 | 0.9084 | 0.9122 |
| 5 | 0.6216 | 0.5883 | 0.4142 | 0.4616 | 0.7897 | 0.8787 | 0.8744 | 0.878 |
| 6 | 0.6149 | 0.5878 | 0.4138 | 0.461 | 0.7287 | 0.846 | 0.8349 | 0.8375 |
| 7 | 0.6111 | 0.5877 | 0.4136 | 0.461 | 0.6678 | 0.811 | 0.7949 | 0.7922 |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 11.858 | 0.331733 | 1140.51 | 46157.5 | 0.0440683 | 0.0491838 | 0.042375 | 0.0401993 |
| 1 | 7.01651e+13 | 0.355304 | 2.55078e+16 | 2.10041e+19 | 0.0952618 | 0.061325 | 0.0759085 | 0.0607388 |
| 2 | 4.29388e+26 | 0.371302 | 5.72407e+29 | inf | 1.86603e+10 | 0.1422 | 1.57574e+11 | 850748 |
| 3 | inf | 0.383174 | inf | inf | 1.6668e+22 | 2.99348e+11 | 2.4731e+24 | 3.50237e+14 |
| 4 | inf | 0.394647 | inf | inf | inf | 1.7959e+24 | inf | 1.44295e+23 |
| 5 | inf | 0.401297 | inf | nan | inf | inf | inf | inf |
| 6 | nan | 0.403797 | nan | nan | inf | inf | inf | inf |
| 7 | nan | 0.404489 | nan | nan | inf | inf | nan | inf |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.282601 | 0.258207 | 1.75176 | 6.79399 | 0.0800112 | 0.0868673 | 0.0773086 | 0.0745843 |
| 1 | 87692.5 | 0.259549 | 6.98239e+06 | 1.39292e+08 | 0.0984425 | 0.0972501 | 0.0907358 | 0.0878206 |
| 2 | 2.16932e+11 | 0.259907 | 3.30754e+13 | 2.9718e+15 | 3814.44 | 0.110695 | 4769.96 | 8.42949 |
| 3 | 5.36647e+17 | 0.260522 | 1.56682e+20 | 6.34032e+22 | 3.60532e+09 | 4297.57 | 1.88969e+10 | 169631 |
| 4 | 1.32756e+24 | 0.261125 | 7.42226e+26 | 1.3527e+30 | 3.40742e+15 | 1.05279e+10 | 7.48632e+16 | 3.44325e+09 |
| 5 | 3.28411e+30 | 0.261441 | inf | nan | 3.22039e+21 | 2.57867e+16 | 2.96584e+23 | 6.989e+13 |
| 6 | nan | 0.2616 | nan | nan | 3.04362e+27 | 6.31611e+22 | 1.17497e+30 | 1.4186e+18 |
| 7 | nan | 0.261658 | nan | nan | inf | 1.54705e+29 | nan | 2.87944e+22 |
predictions_df_10
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.8289 | 0.8031 | 0.713 | 0.6948 | 0.8885 | 0.8898 | 0.8568 | 0.8779 |
| 1 | 0.6774 | 0.6474 | 0.4786 | 0.4955 | 0.8229 | 0.8638 | 0.7727 | 0.8305 |
| 2 | 0.6393 | 0.5971 | 0.43 | 0.4641 | 0.757 | 0.8311 | 0.7102 | 0.7551 |
| 3 | 0.6264 | 0.5745 | 0.4139 | 0.456 | 0.7135 | 0.8018 | 0.6719 | 0.7102 |
| 4 | 0.6181 | 0.5674 | 0.409 | 0.4538 | 0.6681 | 0.7716 | 0.637 | 0.6722 |
| 5 | 0.6112 | 0.5649 | 0.4064 | 0.4523 | 0.6206 | 0.7392 | 0.6039 | 0.6338 |
| 6 | 0.6046 | 0.5647 | 0.4046 | 0.4523 | 0.5736 | 0.7045 | 0.5725 | 0.5961 |
| 7 | 0.6009 | 0.5645 | 0.4047 | 0.4523 | 0.5268 | 0.6701 | 0.5325 | 0.5566 |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 22.5625 | 0.331953 | 507.613 | 18065.2 | 0.488009 | 0.892952 | 4.95772 | 0.744305 |
| 1 | 1.35371e+14 | 0.356419 | 1.13444e+16 | 8.22073e+18 | 1.92517e+11 | 3.47306e+12 | 4.83701e+13 | 1.08407e+08 |
| 2 | 8.28429e+26 | 0.372745 | 2.54573e+29 | inf | 1.71962e+23 | 2.08362e+25 | 7.5916e+26 | 4.463e+16 |
| 3 | inf | 0.384993 | inf | inf | inf | inf | inf | 1.83872e+25 |
| 4 | inf | 0.396741 | inf | inf | inf | inf | inf | inf |
| 5 | inf | 0.403653 | inf | nan | inf | inf | inf | inf |
| 6 | nan | 0.406193 | nan | nan | inf | nan | nan | inf |
| 7 | nan | 0.406886 | nan | nan | nan | nan | nan | inf |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.307521 | 0.259895 | 0.967086 | 2.56955 | 0.187253 | 0.16305 | 0.382042 | 0.193636 |
| 1 | 146240 | 0.260879 | 3.308e+06 | 4.91593e+07 | 45098.7 | 89428 | 1.1445e+06 | 1224.8 |
| 2 | 3.61768e+11 | 0.261185 | 1.56699e+13 | 1.04881e+15 | 4.26259e+10 | 2.19099e+11 | 4.5342e+12 | 2.496e+07 |
| 3 | 8.9494e+17 | 0.261715 | 7.42302e+19 | 2.23763e+22 | 4.02862e+16 | 5.36654e+17 | 1.7963e+19 | 5.06653e+11 |
| 4 | 2.2139e+24 | 0.262176 | 3.51639e+26 | 4.77398e+29 | 3.80748e+22 | 1.31446e+24 | 7.11637e+25 | 1.02839e+16 |
| 5 | 5.47674e+30 | 0.262549 | inf | nan | 3.59849e+28 | 3.2196e+30 | 2.81928e+32 | 2.08739e+20 |
| 6 | nan | 0.262756 | nan | nan | inf | nan | nan | 4.23692e+24 |
| 7 | nan | 0.262827 | nan | nan | nan | nan | nan | 8.59997e+28 |
predictions_df_20
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.7889 | 0.7647 | 0.6929 | 0.6638 | 0.7918 | 0.7956 | 0.7257 | 0.7789 |
| 1 | 0.6502 | 0.6298 | 0.4702 | 0.4861 | 0.7027 | 0.7651 | 0.5815 | 0.6866 |
| 2 | 0.6152 | 0.5846 | 0.4245 | 0.456 | 0.6282 | 0.7304 | 0.5207 | 0.601 |
| 3 | 0.6053 | 0.5622 | 0.4072 | 0.448 | 0.5891 | 0.6962 | 0.4917 | 0.5562 |
| 4 | 0.5967 | 0.5562 | 0.4014 | 0.4467 | 0.5427 | 0.6661 | 0.4642 | 0.5241 |
| 5 | 0.5924 | 0.554 | 0.3993 | 0.4457 | 0.5045 | 0.6389 | 0.4401 | 0.4901 |
| 6 | 0.5861 | 0.5531 | 0.3983 | 0.4452 | 0.4654 | 0.6095 | 0.4155 | 0.4586 |
| 7 | 0.5818 | 0.5528 | 0.398 | 0.445 | 0.4261 | 0.5771 | 0.3912 | 0.4294 |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 28.1916 | 0.331852 | 367.036 | 9175.9 | 1.58508 | 25.2917 | 1658.99 | 2.99281 |
| 1 | 1.70015e+14 | 0.357046 | 8.2019e+15 | 4.17506e+18 | 8.24829e+11 | 1.40847e+14 | 2.57804e+16 | 5.68696e+08 |
| 2 | 1.04044e+27 | 0.373619 | 1.84054e+29 | inf | 7.36764e+23 | 8.44994e+26 | 4.0462e+29 | 2.34152e+17 |
| 3 | inf | 0.386271 | inf | inf | inf | inf | inf | 9.64689e+25 |
| 4 | inf | 0.398429 | inf | inf | inf | inf | inf | inf |
| 5 | inf | 0.40529 | inf | nan | inf | inf | inf | inf |
| 6 | nan | 0.407935 | nan | nan | inf | nan | nan | inf |
| 7 | nan | 0.408804 | nan | nan | nan | nan | nan | inf |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.292307 | 0.261439 | 0.798007 | 1.95752 | 0.321486 | 0.299117 | 1.64464 | 0.377288 |
| 1 | 104532 | 0.262085 | 2.51678e+06 | 3.60469e+07 | 137016 | 392590 | 6.83856e+06 | 4520.07 |
| 2 | 2.58591e+11 | 0.262338 | 1.19219e+13 | 7.6906e+14 | 1.295e+11 | 9.61747e+11 | 2.70923e+13 | 9.20343e+07 |
| 3 | 6.39701e+17 | 0.262748 | 5.64757e+19 | 1.64079e+22 | 1.22392e+17 | 2.35567e+18 | 1.07331e+20 | 1.86815e+12 |
| 4 | 1.58249e+24 | 0.263168 | 2.67533e+26 | 3.50061e+29 | 1.15674e+23 | 5.7699e+24 | 4.2521e+26 | 3.79192e+16 |
| 5 | 3.91476e+30 | 0.263499 | inf | nan | 1.09324e+29 | 1.41326e+31 | inf | 7.69671e+20 |
| 6 | nan | 0.263669 | nan | nan | inf | nan | nan | 1.56225e+25 |
| 7 | nan | 0.26375 | nan | nan | nan | nan | nan | 3.17101e+29 |
predictions_df_30
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.7295 | 0.7188 | 0.6602 | 0.6352 | 0.7123 | 0.7062 | 0.6092 | 0.678 |
| 1 | 0.6226 | 0.5947 | 0.4685 | 0.4713 | 0.6087 | 0.662 | 0.4505 | 0.5623 |
| 2 | 0.5965 | 0.5561 | 0.4117 | 0.4378 | 0.5338 | 0.6335 | 0.4017 | 0.4778 |
| 3 | 0.5862 | 0.5362 | 0.3957 | 0.4283 | 0.4909 | 0.6057 | 0.3767 | 0.4411 |
| 4 | 0.581 | 0.5289 | 0.3901 | 0.4273 | 0.4511 | 0.5801 | 0.3575 | 0.4154 |
| 5 | 0.5756 | 0.5272 | 0.388 | 0.4271 | 0.4146 | 0.5562 | 0.3396 | 0.3847 |
| 6 | 0.5706 | 0.5266 | 0.3872 | 0.4272 | 0.3816 | 0.5327 | 0.3197 | 0.3594 |
| 7 | 0.5662 | 0.5265 | 0.3864 | 0.4271 | 0.3578 | 0.5075 | 0.2944 | 0.3346 |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.35147 | 0.332484 | 204.824 | 30276.8 | 2.49049 | 1107.42 | 6052.16 | 6.64916 |
| 1 | 1.13041e+11 | 0.357981 | 4.57489e+15 | 1.37789e+19 | 1.37425e+12 | 6.58275e+15 | 9.42148e+16 | 1.38866e+09 |
| 2 | 6.91776e+23 | 0.375042 | 1.02663e+29 | inf | 1.22752e+24 | 3.94925e+28 | 1.47869e+30 | 5.71789e+17 |
| 3 | inf | 0.388116 | inf | inf | inf | inf | inf | 2.35573e+26 |
| 4 | inf | 0.400985 | inf | inf | inf | inf | inf | inf |
| 5 | inf | 0.408253 | inf | nan | inf | inf | inf | inf |
| 6 | nan | 0.4109 | nan | nan | inf | nan | nan | inf |
| 7 | nan | 0.411732 | nan | nan | nan | nan | nan | inf |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.252483 | 0.26392 | 0.520379 | 3.08801 | 0.416441 | 1.11994 | 4.48711 | 0.595055 |
| 1 | 2695.64 | 0.263854 | 1.21471e+06 | 6.00994e+07 | 197777 | 2.5163e+06 | 1.92178e+07 | 8955.93 |
| 2 | 6.66792e+09 | 0.263932 | 5.75406e+12 | 1.28222e+15 | 1.86926e+11 | 6.16374e+12 | 7.61351e+13 | 1.82292e+08 |
| 3 | 1.64951e+16 | 0.264135 | 2.72578e+19 | 2.73561e+22 | 1.76666e+17 | 1.50973e+19 | 3.01622e+20 | 3.70022e+12 |
| 4 | 4.08055e+22 | 0.264517 | 1.29124e+26 | 5.83641e+29 | 1.66969e+23 | 3.69787e+25 | 1.19493e+27 | 7.51059e+16 |
| 5 | 1.00945e+29 | 0.264861 | inf | nan | 1.57804e+29 | 9.05743e+31 | inf | 1.52448e+21 |
| 6 | nan | 0.265062 | nan | nan | inf | nan | nan | 3.09433e+25 |
| 7 | nan | 0.265141 | nan | nan | nan | nan | nan | 6.28078e+29 |
predictions_df_40
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.6758 | 0.6712 | 0.6345 | 0.5949 | 0.6465 | 0.6307 | 0.5319 | 0.5941 |
| 1 | 0.594 | 0.5476 | 0.451 | 0.4426 | 0.5315 | 0.5912 | 0.3701 | 0.4646 |
| 2 | 0.5717 | 0.5193 | 0.4003 | 0.4106 | 0.4549 | 0.5582 | 0.3237 | 0.391 |
| 3 | 0.563 | 0.5002 | 0.3839 | 0.4063 | 0.4084 | 0.5308 | 0.3029 | 0.3593 |
| 4 | 0.5567 | 0.4942 | 0.3803 | 0.4052 | 0.376 | 0.506 | 0.2878 | 0.3331 |
| 5 | 0.5529 | 0.491 | 0.3792 | 0.4048 | 0.3467 | 0.4847 | 0.2741 | 0.3163 |
| 6 | 0.5483 | 0.4904 | 0.3783 | 0.4047 | 0.3172 | 0.4674 | 0.2642 | 0.2965 |
| 7 | 0.5437 | 0.4902 | 0.3779 | 0.4048 | 0.2961 | 0.4438 | 0.244 | 0.2796 |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.334449 | 0.33355 | 166.198 | 272.237 | 3.66469 | 5455.45 | 6631.49 | 13.0949 |
| 1 | 7.08332e+06 | 0.360352 | 3.70999e+15 | 1.23569e+17 | 2.11366e+12 | 3.25487e+16 | 1.0285e+17 | 2.95056e+09 |
| 2 | 4.33474e+19 | 0.377944 | 8.32537e+28 | 5.62461e+31 | 1.88799e+24 | 1.95273e+29 | 1.61422e+30 | 1.21497e+18 |
| 3 | inf | 0.391355 | inf | inf | inf | inf | inf | 5.00559e+26 |
| 4 | inf | 0.404701 | inf | inf | inf | inf | inf | inf |
| 5 | inf | 0.412552 | inf | nan | inf | inf | inf | inf |
| 6 | inf | 0.415513 | nan | nan | inf | nan | nan | inf |
| 7 | nan | 0.416366 | nan | nan | nan | nan | nan | inf |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.254736 | 0.26692 | 0.515336 | 0.491423 | 0.521977 | 2.91956 | 6.35372 | 0.872454 |
| 1 | 23.2818 | 0.266569 | 1.18494e+06 | 4.64837e+06 | 273318 | 7.18149e+06 | 2.7821e+07 | 15278.9 |
| 2 | 5.69535e+07 | 0.266385 | 5.61305e+12 | 9.91727e+13 | 2.58323e+11 | 1.75909e+13 | 1.10218e+14 | 3.10904e+08 |
| 3 | 1.40891e+14 | 0.266581 | 2.65898e+19 | 2.11585e+21 | 2.44144e+17 | 4.30864e+19 | 4.36648e+20 | 6.31083e+12 |
| 4 | 3.48537e+20 | 0.266916 | 1.25959e+26 | 4.51415e+28 | 2.30743e+23 | 1.05534e+26 | 1.72986e+27 | 1.28095e+17 |
| 5 | 8.6221e+26 | 0.267193 | inf | nan | 2.18077e+29 | 2.58492e+32 | inf | 2.60004e+21 |
| 6 | inf | 0.267391 | nan | nan | inf | nan | nan | 5.27747e+25 |
| 7 | nan | 0.267474 | nan | nan | nan | nan | nan | 1.0712e+30 |
predictions_df_50
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.613 | 0.6099 | 0.5924 | 0.5624 | 0.5778 | 0.544 | 0.4557 | 0.5103 |
| 1 | 0.5501 | 0.5111 | 0.4397 | 0.4173 | 0.4568 | 0.5042 | 0.3028 | 0.3663 |
| 2 | 0.5353 | 0.4866 | 0.3854 | 0.3849 | 0.385 | 0.4765 | 0.2652 | 0.3058 |
| 3 | 0.5252 | 0.4703 | 0.3689 | 0.3817 | 0.3462 | 0.4542 | 0.2499 | 0.2813 |
| 4 | 0.5202 | 0.463 | 0.3622 | 0.3804 | 0.3121 | 0.435 | 0.2399 | 0.2675 |
| 5 | 0.5164 | 0.4611 | 0.3609 | 0.3802 | 0.2836 | 0.4168 | 0.2294 | 0.2525 |
| 6 | 0.5129 | 0.4608 | 0.3599 | 0.38 | 0.2574 | 0.4001 | 0.2161 | 0.2372 |
| 7 | 0.5099 | 0.461 | 0.3594 | 0.3797 | 0.2402 | 0.3795 | 0.2044 | 0.2254 |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 1.58543 | 0.336038 | 95.394 | 1138.36 | 289.098 | 31656.9 | 17426.4 | 25.5181 |
| 1 | 7.50993e+12 | 8.00312e+09 | 2.12785e+15 | 5.17658e+17 | 2.56059e+14 | 1.89295e+17 | 2.71098e+17 | 6.11499e+09 |
| 2 | 4.59583e+25 | 7.23421e+24 | 4.77499e+28 | inf | 2.28721e+26 | 1.13565e+30 | 4.25484e+30 | 2.5181e+18 |
| 3 | inf | inf | inf | inf | inf | inf | inf | 1.03744e+27 |
| 4 | inf | inf | inf | inf | inf | inf | inf | inf |
| 5 | inf | inf | inf | nan | inf | inf | inf | inf |
| 6 | nan | nan | nan | nan | inf | nan | nan | inf |
| 7 | nan | nan | nan | nan | nan | nan | nan | inf |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.266141 | 0.269467 | 0.38141 | 0.65657 | 0.762779 | 10.8588 | 11.151 | 1.2592 |
| 1 | 22251.5 | 709.866 | 553413 | 8.08543e+06 | 483673 | 2.75611e+07 | 4.85226e+07 | 24645.7 |
| 2 | 5.5045e+10 | 2.13386e+10 | 2.62156e+12 | 1.72502e+14 | 4.57132e+11 | 6.75091e+13 | 1.92232e+14 | 5.01398e+08 |
| 3 | 1.3617e+17 | 6.41552e+17 | 1.24187e+19 | 3.68033e+21 | 4.3204e+17 | 1.65354e+20 | 7.61559e+20 | 1.01775e+13 |
| 4 | 3.36858e+23 | 1.92885e+25 | 5.8829e+25 | 7.85197e+28 | 4.08325e+23 | 4.05013e+26 | 3.01705e+27 | 2.0658e+17 |
| 5 | 8.33318e+29 | inf | inf | nan | 3.85912e+29 | 9.92025e+32 | inf | 4.19309e+21 |
| 6 | nan | nan | nan | nan | inf | nan | nan | 8.511e+25 |
| 7 | nan | nan | nan | nan | nan | nan | nan | 1.72753e+30 |
predictions_df_60
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.5477 | 0.5464 | 0.5438 | 0.5003 | 0.5337 | 0.4792 | 0.3887 | 0.443 |
| 1 | 0.5041 | 0.4692 | 0.4078 | 0.3771 | 0.4083 | 0.438 | 0.2434 | 0.2985 |
| 2 | 0.4916 | 0.4487 | 0.3623 | 0.3516 | 0.3291 | 0.4141 | 0.2159 | 0.2439 |
| 3 | 0.4859 | 0.4362 | 0.3439 | 0.3473 | 0.289 | 0.3998 | 0.2035 | 0.2256 |
| 4 | 0.4836 | 0.4317 | 0.3401 | 0.346 | 0.261 | 0.3843 | 0.1918 | 0.2144 |
| 5 | 0.4809 | 0.43 | 0.3379 | 0.3467 | 0.2375 | 0.3724 | 0.1859 | 0.2036 |
| 6 | 0.4772 | 0.4295 | 0.3371 | 0.3464 | 0.2162 | 0.3543 | 0.1778 | 0.1907 |
| 7 | 0.4733 | 0.4292 | 0.3365 | 0.3462 | 0.2044 | 0.3355 | 0.1665 | 0.181 |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.345818 | 0.338227 | 116.179 | 0.317512 | 192.055 | 56842.2 | 31114.9 | 38.1415 |
| 1 | 9.52198e+08 | 0.365955 | 2.59052e+15 | 0.383506 | 1.69408e+14 | 3.39952e+17 | 4.84942e+17 | 9.3244e+09 |
| 2 | 5.82714e+21 | 0.384757 | 5.81324e+28 | 1205.03 | 1.51321e+26 | 2.03951e+30 | 7.61109e+30 | 3.83973e+18 |
| 3 | inf | 0.398697 | inf | 5.4801e+17 | inf | inf | inf | 1.58195e+27 |
| 4 | inf | 0.412394 | inf | inf | inf | inf | inf | inf |
| 5 | inf | 0.420297 | inf | inf | inf | inf | inf | inf |
| 6 | inf | 0.423409 | nan | inf | inf | nan | nan | inf |
| 7 | nan | 0.424448 | nan | nan | nan | nan | nan | inf |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.261175 | 0.27228 | 0.414712 | 0.281871 | 0.828239 | 19.355 | 16.2308 | 1.64474 |
| 1 | 291.453 | 0.271055 | 697474 | 0.291952 | 520851 | 4.93893e+07 | 7.01351e+07 | 34098.7 |
| 2 | 7.20409e+08 | 0.270727 | 3.30395e+12 | 0.586689 | 4.9227e+11 | 1.20975e+14 | 2.77854e+14 | 6.93647e+08 |
| 3 | 1.78215e+15 | 0.270666 | 1.56513e+19 | 6.14024e+06 | 4.65249e+17 | 2.96313e+20 | 1.10076e+21 | 1.40798e+13 |
| 4 | 4.40867e+21 | 0.270837 | 7.41422e+25 | 1.31002e+14 | 4.39712e+23 | 7.2578e+26 | 4.36087e+27 | 2.85788e+17 |
| 5 | 1.09062e+28 | 0.271108 | inf | 2.79492e+21 | 4.15576e+29 | 1.7777e+33 | inf | 5.80083e+21 |
| 6 | inf | 0.271319 | nan | 5.96294e+28 | inf | nan | nan | 1.17743e+26 |
| 7 | nan | 0.271411 | nan | nan | nan | nan | nan | 2.38992e+30 |
predictions_df_70
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.4783 | 0.4807 | 0.4929 | 0.4542 | 0.4733 | 0.4209 | 0.3451 | 0.3804 |
| 1 | 0.4577 | 0.4054 | 0.3859 | 0.3507 | 0.3517 | 0.3739 | 0.2119 | 0.2329 |
| 2 | 0.4469 | 0.3866 | 0.3428 | 0.3276 | 0.2807 | 0.3514 | 0.1815 | 0.1977 |
| 3 | 0.44 | 0.3738 | 0.3249 | 0.3234 | 0.248 | 0.3388 | 0.1716 | 0.1838 |
| 4 | 0.4368 | 0.3703 | 0.3207 | 0.3217 | 0.2246 | 0.3279 | 0.1661 | 0.1752 |
| 5 | 0.4345 | 0.3699 | 0.318 | 0.3209 | 0.2038 | 0.3144 | 0.1605 | 0.1665 |
| 6 | 0.4316 | 0.3694 | 0.3173 | 0.3212 | 0.1891 | 0.3002 | 0.1499 | 0.1595 |
| 7 | 0.4299 | 0.3695 | 0.3169 | 0.3211 | 0.18 | 0.287 | 0.1465 | 0.1523 |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.350878 | 0.343233 | 93.8624 | 3436.76 | 265.853 | 127984 | 65187.2 | 63.0467 |
| 1 | 2.90657e+08 | 4.31318e+11 | 2.09122e+15 | 1.56376e+18 | 2.33798e+14 | 7.66012e+17 | 1.01754e+18 | 1.58977e+10 |
| 2 | 1.77872e+21 | 3.89879e+26 | 4.69278e+28 | inf | 2.08836e+26 | 4.59561e+30 | 1.59701e+31 | 6.5467e+18 |
| 3 | inf | inf | inf | inf | inf | inf | inf | 2.6972e+27 |
| 4 | inf | inf | inf | inf | inf | inf | inf | inf |
| 5 | inf | inf | inf | nan | inf | inf | inf | inf |
| 6 | inf | nan | nan | nan | inf | nan | nan | inf |
| 7 | nan | nan | nan | nan | nan | nan | nan | inf |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.265043 | 0.276687 | 0.407133 | 0.804195 | 1.14616 | 34.5695 | 26.3127 | 2.21781 |
| 1 | 207.179 | 5210.41 | 655931 | 1.10637e+07 | 816719 | 8.80236e+07 | 1.12207e+08 | 48726.8 |
| 2 | 5.11911e+08 | 1.56652e+11 | 3.10726e+12 | 2.36043e+14 | 7.719e+11 | 2.15607e+14 | 4.44529e+14 | 9.91106e+08 |
| 3 | 1.26637e+15 | 4.70978e+18 | 1.47195e+19 | 5.03597e+21 | 7.2953e+17 | 5.281e+20 | 1.76108e+21 | 2.01177e+13 |
| 4 | 3.13273e+21 | 1.41601e+26 | 6.97283e+25 | 1.07442e+29 | 6.89487e+23 | 1.29351e+27 | 6.97682e+27 | 4.08342e+17 |
| 5 | 7.74974e+27 | inf | inf | nan | 6.51641e+29 | inf | inf | 8.2884e+21 |
| 6 | inf | nan | nan | nan | inf | nan | nan | 1.68235e+26 |
| 7 | nan | nan | nan | nan | nan | nan | nan | 3.41479e+30 |
predictions_df_80
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.4168 | 0.419 | 0.4463 | 0.4005 | 0.4121 | 0.3612 | 0.2934 | 0.3231 |
| 1 | 0.4157 | 0.3629 | 0.3531 | 0.3123 | 0.2955 | 0.3235 | 0.1775 | 0.1873 |
| 2 | 0.4084 | 0.3431 | 0.313 | 0.2923 | 0.2277 | 0.3034 | 0.1581 | 0.1584 |
| 3 | 0.4053 | 0.3388 | 0.2993 | 0.2867 | 0.1998 | 0.2915 | 0.1524 | 0.1501 |
| 4 | 0.4023 | 0.3364 | 0.2961 | 0.2878 | 0.1829 | 0.2811 | 0.1483 | 0.1444 |
| 5 | 0.4004 | 0.3341 | 0.295 | 0.2875 | 0.1731 | 0.27 | 0.144 | 0.1388 |
| 6 | 0.3976 | 0.3344 | 0.2946 | 0.2873 | 0.1597 | 0.2557 | 0.1435 | 0.1351 |
| 7 | 0.3952 | 0.3343 | 0.2938 | 0.2873 | 0.1525 | 0.2473 | 0.1318 | 0.1277 |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.36119 | 0.348424 | 2748.09 | 128.418 | 4936.27 | 242266 | 64221.1 | 88.9256 |
| 1 | 2.88879e+09 | 0.378737 | 6.15886e+16 | 5.82331e+16 | 4.39462e+15 | 1.4504e+18 | 1.00127e+18 | 2.2792e+10 |
| 2 | 1.76784e+22 | 0.397657 | 1.38208e+30 | 2.65066e+31 | 3.92542e+27 | 8.70153e+30 | 1.57148e+31 | 9.38586e+18 |
| 3 | inf | 0.410796 | inf | inf | inf | inf | inf | 3.86691e+27 |
| 4 | inf | 0.424774 | inf | inf | inf | inf | inf | inf |
| 5 | inf | 0.433369 | inf | nan | inf | inf | inf | inf |
| 6 | inf | 0.436835 | nan | nan | nan | nan | nan | inf |
| 7 | nan | 0.437946 | nan | nan | nan | nan | nan | inf |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.270721 | 0.280256 | 1.60147 | 0.384265 | 3.50793 | 61.061 | 29.5184 | 2.7358 |
| 1 | 997.664 | 0.278353 | 6.33809e+06 | 2.00159e+06 | 3.08597e+06 | 1.55189e+08 | 1.2669e+08 | 62037.6 |
| 2 | 2.46756e+09 | 0.277853 | 3.0025e+13 | 4.27039e+13 | 2.91659e+12 | 3.80122e+14 | 5.01907e+14 | 1.26177e+09 |
| 3 | 6.10425e+15 | 0.277661 | 1.42233e+20 | 9.11087e+20 | 2.7565e+18 | 9.31058e+20 | 1.98839e+21 | 2.56116e+13 |
| 4 | 1.51007e+22 | 0.277708 | 6.73775e+26 | 1.9438e+28 | 2.6052e+24 | 2.2805e+27 | 7.87736e+27 | 5.19856e+17 |
| 5 | 3.7356e+28 | 0.277908 | inf | nan | 2.4622e+30 | inf | inf | 1.05519e+22 |
| 6 | inf | 0.278071 | nan | nan | nan | nan | nan | 2.14179e+26 |
| 7 | nan | 0.278143 | nan | nan | nan | nan | nan | 4.34733e+30 |
predictions_df_90
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.3568 | 0.3585 | 0.3858 | 0.3497 | 0.3576 | 0.3033 | 0.2643 | 0.2807 |
| 1 | 0.3566 | 0.3165 | 0.3156 | 0.2773 | 0.245 | 0.2706 | 0.1556 | 0.1532 |
| 2 | 0.3521 | 0.303 | 0.2789 | 0.2533 | 0.1883 | 0.26 | 0.1428 | 0.1335 |
| 3 | 0.3471 | 0.2976 | 0.2637 | 0.2487 | 0.1681 | 0.2479 | 0.1378 | 0.1283 |
| 4 | 0.3451 | 0.2937 | 0.2607 | 0.249 | 0.1525 | 0.2381 | 0.1347 | 0.1239 |
| 5 | 0.3428 | 0.2943 | 0.2602 | 0.2487 | 0.1444 | 0.2316 | 0.1317 | 0.121 |
| 6 | 0.3423 | 0.2946 | 0.2603 | 0.2487 | 0.1361 | 0.2135 | 0.1256 | 0.1174 |
| 7 | 0.3404 | 0.2945 | 0.2606 | 0.2488 | 0.1378 | 0.2076 | 0.1223 | 0.1161 |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.723914 | 0.353494 | 8862.38 | 6064.18 | 13319.2 | 410721 | 114378 | 127.622 |
| 1 | 2.10742e+12 | 2.76552e+10 | 1.98685e+17 | 2.7594e+18 | 1.18623e+16 | 2.4594e+18 | 1.78621e+18 | 3.31004e+10 |
| 2 | 1.28967e+25 | 2.49982e+25 | 4.45858e+30 | inf | 1.05958e+28 | 1.47549e+31 | 2.80344e+31 | 1.3631e+19 |
| 3 | inf | inf | inf | inf | inf | inf | inf | 5.61588e+27 |
| 4 | inf | inf | inf | inf | inf | inf | inf | inf |
| 5 | inf | inf | inf | nan | inf | inf | inf | inf |
| 6 | nan | nan | nan | nan | nan | nan | nan | inf |
| 7 | nan | nan | nan | nan | nan | nan | nan | inf |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.280915 | 0.283274 | 3.53546 | 1.15982 | 8.90369 | 97.2548 | 38.9854 | 3.50805 |
| 1 | 12401.7 | 1322.91 | 1.55567e+07 | 1.8453e+07 | 8.28434e+06 | 2.4694e+08 | 1.66078e+08 | 82183 |
| 2 | 3.06786e+10 | 3.97701e+10 | 7.36958e+13 | 3.93695e+14 | 7.82964e+12 | 6.04858e+14 | 6.57949e+14 | 1.6714e+09 |
| 3 | 7.58928e+16 | 1.1957e+18 | 3.49107e+20 | 8.39946e+21 | 7.39987e+18 | 1.48152e+21 | 2.60658e+21 | 3.39264e+13 |
| 4 | 1.87743e+23 | 3.59491e+25 | 1.65377e+27 | 1.79202e+29 | 6.99369e+24 | 3.62878e+27 | 1.03264e+28 | 6.88627e+17 |
| 5 | 4.64439e+29 | inf | inf | nan | 6.60981e+30 | inf | inf | 1.39775e+22 |
| 6 | nan | nan | nan | nan | nan | nan | nan | 2.83711e+26 |
| 7 | nan | nan | nan | nan | nan | nan | nan | 5.75869e+30 |
predictions_df_100
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.2963 | 0.291 | 0.3201 | 0.2991 | 0.3121 | 0.2589 | 0.2221 | 0.2454 |
| 1 | 0.3045 | 0.261 | 0.2636 | 0.2468 | 0.2088 | 0.2251 | 0.1343 | 0.1277 |
| 2 | 0.2998 | 0.2534 | 0.2322 | 0.23 | 0.1652 | 0.2137 | 0.1248 | 0.1201 |
| 3 | 0.2991 | 0.2496 | 0.2191 | 0.2282 | 0.147 | 0.2081 | 0.1198 | 0.1176 |
| 4 | 0.2967 | 0.2476 | 0.2174 | 0.2289 | 0.1353 | 0.199 | 0.1172 | 0.1167 |
| 5 | 0.2953 | 0.2464 | 0.2167 | 0.2282 | 0.1266 | 0.1943 | 0.1156 | 0.1144 |
| 6 | 0.2936 | 0.2462 | 0.2166 | 0.2276 | 0.1206 | 0.1828 | 0.1108 | 0.1152 |
| 7 | 0.292 | 0.2464 | 0.2162 | 0.2276 | 0.1216 | 0.1775 | 0.106 | 0.1137 |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 3.09084 | 0.367812 | 95160.2 | 0.34763 | 62374.5 | 947791 | 172409 | 176.613 |
| 1 | 1.64076e+13 | 3.2722e+12 | 2.13445e+18 | 3.10789e+06 | 5.56086e+16 | 5.67781e+18 | 2.69351e+18 | 4.64529e+10 |
| 2 | 1.00409e+26 | 2.95782e+27 | 4.7898e+31 | 1.41464e+21 | 4.96714e+28 | 3.40634e+31 | 4.22742e+31 | 1.91298e+19 |
| 3 | inf | inf | inf | inf | inf | inf | inf | 7.88136e+27 |
| 4 | inf | inf | inf | inf | inf | inf | inf | inf |
| 5 | inf | inf | inf | inf | inf | inf | inf | inf |
| 6 | nan | nan | nan | nan | nan | nan | nan | inf |
| 7 | nan | nan | nan | nan | nan | nan | nan | inf |
| normal_dim_tied_iteration256 10_Targets | normal_dim_tied_iteration128 10_Targets | normal_dim_tied_iteration64 10_Targets | normal_dim_tied_iteration32 10_Targets | normal_dim_tied_iteration256 Mnist | normal_dim_tied_iteration128 Mnist | normal_dim_tied_iteration64 Mnist | normal_dim_tied_iteration32 Mnist | |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.295359 | 0.2887 | 17.1987 | 0.300294 | 28.169 | 187.022 | 54.1196 | 4.27913 |
| 1 | 35141.5 | 18686.4 | 8.06622e+07 | 17.4209 | 2.67849e+07 | 4.72439e+08 | 2.28884e+08 | 102476 |
| 2 | 8.69332e+10 | 5.61821e+11 | 3.82115e+14 | 3.65014e+08 | 2.53147e+13 | 1.15719e+15 | 9.06765e+14 | 2.08401e+09 |
| 3 | 2.15055e+17 | 1.68913e+19 | 1.81013e+21 | 7.78756e+15 | 2.39252e+19 | 2.83439e+21 | 3.5923e+21 | 4.23015e+13 |
| 4 | 5.32003e+23 | 5.07844e+26 | 8.57484e+27 | 1.66147e+23 | 2.26119e+25 | 6.94245e+27 | 1.42315e+28 | 8.58623e+17 |
| 5 | 1.31607e+30 | inf | inf | 3.54475e+30 | 2.13708e+31 | inf | inf | 1.74281e+22 |
| 6 | nan | nan | nan | nan | nan | nan | nan | 3.53749e+26 |
| 7 | nan | nan | nan | nan | nan | nan | nan | 7.18029e+30 |
/home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:397: UserWarning: Warning: converting a masked element to nan. dv = (np.float64(self.norm.vmax) - /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:398: UserWarning: Warning: converting a masked element to nan. np.float64(self.norm.vmin)) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:405: UserWarning: Warning: converting a masked element to nan. a_min = np.float64(newmin) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:410: UserWarning: Warning: converting a masked element to nan. a_max = np.float64(newmax) <string>:6: UserWarning: Warning: converting a masked element to nan. /home/hicky/anaconda3/lib/python3.7/site-packages/numpy/ma/core.py:711: UserWarning: Warning: converting a masked element to nan. data = np.array(a, copy=False, subok=subok)
/home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:397: UserWarning: Warning: converting a masked element to nan. dv = (np.float64(self.norm.vmax) - /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:398: UserWarning: Warning: converting a masked element to nan. np.float64(self.norm.vmin)) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:405: UserWarning: Warning: converting a masked element to nan. a_min = np.float64(newmin) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:410: UserWarning: Warning: converting a masked element to nan. a_max = np.float64(newmax) <string>:6: UserWarning: Warning: converting a masked element to nan. /home/hicky/anaconda3/lib/python3.7/site-packages/numpy/ma/core.py:711: UserWarning: Warning: converting a masked element to nan. data = np.array(a, copy=False, subok=subok)
/home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:397: UserWarning: Warning: converting a masked element to nan. dv = (np.float64(self.norm.vmax) - /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:398: UserWarning: Warning: converting a masked element to nan. np.float64(self.norm.vmin)) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:405: UserWarning: Warning: converting a masked element to nan. a_min = np.float64(newmin) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:410: UserWarning: Warning: converting a masked element to nan. a_max = np.float64(newmax) <string>:6: UserWarning: Warning: converting a masked element to nan. /home/hicky/anaconda3/lib/python3.7/site-packages/numpy/ma/core.py:711: UserWarning: Warning: converting a masked element to nan. data = np.array(a, copy=False, subok=subok)
/home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:397: UserWarning: Warning: converting a masked element to nan. dv = (np.float64(self.norm.vmax) - /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:398: UserWarning: Warning: converting a masked element to nan. np.float64(self.norm.vmin)) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:405: UserWarning: Warning: converting a masked element to nan. a_min = np.float64(newmin) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:410: UserWarning: Warning: converting a masked element to nan. a_max = np.float64(newmax) <string>:6: UserWarning: Warning: converting a masked element to nan. /home/hicky/anaconda3/lib/python3.7/site-packages/numpy/ma/core.py:711: UserWarning: Warning: converting a masked element to nan. data = np.array(a, copy=False, subok=subok)
/home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:397: UserWarning: Warning: converting a masked element to nan. dv = (np.float64(self.norm.vmax) - /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:398: UserWarning: Warning: converting a masked element to nan. np.float64(self.norm.vmin)) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:405: UserWarning: Warning: converting a masked element to nan. a_min = np.float64(newmin) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:410: UserWarning: Warning: converting a masked element to nan. a_max = np.float64(newmax) <string>:6: UserWarning: Warning: converting a masked element to nan. /home/hicky/anaconda3/lib/python3.7/site-packages/numpy/ma/core.py:711: UserWarning: Warning: converting a masked element to nan. data = np.array(a, copy=False, subok=subok)
/home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:397: UserWarning: Warning: converting a masked element to nan. dv = (np.float64(self.norm.vmax) - /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:398: UserWarning: Warning: converting a masked element to nan. np.float64(self.norm.vmin)) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:405: UserWarning: Warning: converting a masked element to nan. a_min = np.float64(newmin) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:410: UserWarning: Warning: converting a masked element to nan. a_max = np.float64(newmax) <string>:6: UserWarning: Warning: converting a masked element to nan. /home/hicky/anaconda3/lib/python3.7/site-packages/numpy/ma/core.py:711: UserWarning: Warning: converting a masked element to nan. data = np.array(a, copy=False, subok=subok)
/home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:397: UserWarning: Warning: converting a masked element to nan. dv = (np.float64(self.norm.vmax) - /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:398: UserWarning: Warning: converting a masked element to nan. np.float64(self.norm.vmin)) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:405: UserWarning: Warning: converting a masked element to nan. a_min = np.float64(newmin) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:410: UserWarning: Warning: converting a masked element to nan. a_max = np.float64(newmax) <string>:6: UserWarning: Warning: converting a masked element to nan. /home/hicky/anaconda3/lib/python3.7/site-packages/numpy/ma/core.py:711: UserWarning: Warning: converting a masked element to nan. data = np.array(a, copy=False, subok=subok)
/home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:397: UserWarning: Warning: converting a masked element to nan. dv = (np.float64(self.norm.vmax) - /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:398: UserWarning: Warning: converting a masked element to nan. np.float64(self.norm.vmin)) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:405: UserWarning: Warning: converting a masked element to nan. a_min = np.float64(newmin) /home/hicky/anaconda3/lib/python3.7/site-packages/matplotlib/image.py:410: UserWarning: Warning: converting a masked element to nan. a_max = np.float64(newmax) <string>:6: UserWarning: Warning: converting a masked element to nan. /home/hicky/anaconda3/lib/python3.7/site-packages/numpy/ma/core.py:711: UserWarning: Warning: converting a masked element to nan. data = np.array(a, copy=False, subok=subok)
